Symmetry Understanding of 3D Shapes via Chirality Disentanglement
Not on the map. Why?
Abstract (arXiv)
Chirality information (i.e. information that allows distinguishing left from right) is ubiquitous for various data modes in computer vision, including images, videos, point clouds, and meshes. While chirality has been extensively studied in the image domain, its exploration in shape analysis (such as point clouds and meshes) remains underdeveloped. Although many shape vertex descriptors have shown appealing properties (e.g. robustness to rigid-body transformations), they are often not able to disambiguate between left and right symmetric parts. Considering the ubiquity of chirality information in different shape analysis problems and the lack of chirality-aware features within current shape descriptors, developing a chirality feature extractor becomes necessary and urgent. Based on the recent Diff3F framework, we propose an unsupervised chirality feature extraction pipeline to decorate shape vertices with chirality-aware information, extracted from 2D foundation models. We evaluated the extracted chirality features through quantitative and qualitative experiments across diverse datasets. Results from downstream tasks including left-right disentanglement, shape matching, and part segmentation demonstrate their effectiveness and practical utility. Project page: https://wei-kang-wang.github.io/chirality/
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 39 of its 74 references that are in the map. First posted on arXiv 7 Aug 2025.
Builds on
39 of 74 references.
References · 39
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
- 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
- 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
- 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
- 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,503
- 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
- 2019Deep Closest Point: Learning Representations for Point Cloud Registrationcited by 321
- 20163D Menagerie: Modeling the 3D shape and pose of animalscited by 312
- 2020RPM-Net: Robust Point Matching using Learned Featurescited by 182
- 2019Unsupervised Learning of Probably Symmetric Deformable 3D Objects from Images in the Wildcited by 180
- 20183D-CODED : 3D Correspondences by Deep Deformationcited by 160
- 2020Deep Geometric Functional Maps: Robust Feature Learning for Shape Correspondencecited by 125
27 more
- 2023Unsupervised Semantic Correspondence Using Stable Diffusioncited by 120
- 2022MagicPony: Learning Articulated 3D Animals in the Wildcited by 112
- 2019Learning elementary structures for 3D shape generation and matchingcited by 98
- 2023Telling Left from Right: Identifying Geometry-Aware Semantic Correspondencecited by 86
- 2021DPFM: Deep Partial Functional Mapscited by 58
- 2023Diffusion 3D Features (Diff3F): Decorating Untextured Shapes with Distilled Semantic Featurescited by 55
- 2023FeatureNeRF: Learning Generalizable NeRFs by Distilling Foundation Modelscited by 47
- 2023Generative Adversarial Symmetry Discoverycited by 42
- 2022Unsupervised Deep Multi-Shape Matchingcited by 39
- 2022Smooth Non-Rigid Shape Matching via Effective Dirichlet Energy Optimizationcited by 37
- 2020Dual Geometric Graph Network (DG2N) -- Iterative network for deformable shape alignmentcited by 35
- 2024DenseMatcher: Learning 3D Semantic Correspondence for Category-Level Manipulation from a Single Democited by 34
- 2019On Object Symmetries and 6D Pose Estimation from Imagescited by 33
- 2020Isometric Multi-Shape Matchingcited by 33
- 2019Chirality Nets for Human Pose Regressioncited by 31
- 2022Symmetry and Uncertainty-Aware Object SLAM for 6DoF Object Pose Estimationcited by 28
- 2020Structured Regularization of Functional Map Computationscited by 26
- 2020MINA: Convex Mixed-Integer Programming for Non-Rigid Shape Alignmentcited by 20
- 2022A Scalable Combinatorial Solver for Elastic Geometrically Consistent 3D Shape Matchingcited by 19
- 2023SE-ORNet: Self-Ensembling Orientation-aware Network for Unsupervised Point Cloud Shape Correspondencecited by 19
- 2018Pose Estimation for Objects with Rotational Symmetrycited by 15
- 2023Unsupervised Keypoints from Pretrained Diffusion Modelscited by 15
- 2020Visual Chiralitycited by 14
- 2024Robust Symmetry Detection via Riemannian Langevin Dynamicscited by 14
- 2024Beyond Complete Shapes: A Benchmark for Quantitative Evaluation of 3D Shape Surface Matching Algorithmscited by 11
- 2024A Generative Model of Symmetry Transformationscited by 10
- 2018Fast and Accurate Intrinsic Symmetry Detectioncited by 7
Built on by
Citing papers per year: 2026: 3.
3 papers.